Computing device state or activity based task reminders and automatic tracking of statuses of task-related activities are provided. Users are enabled to create reminders that are triggered based on a device state of the user's device or activity signals from the operating system, an application, or a user file. The status of a task item can be inferred from signals collected from one or more sources. The signals provide information associated with tasks that the user performs in various life events. Machine learning, statistical analysis, behavioral analytics, and data mining techniques are applied to the signals, and the user's activities are mapped to task items that the user has created. An inferred status of a task activity can be shared with other systems, or can be used for a variety of functions (e.g., to automatically update the user's task list, or to remind the user of an uncompleted task item).
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The system of claim 1, wherein the instructions that, when executed by the at least one processing device, further cause the system to determine a match between a task-related entity of the one or more task-related entities and an entity of the user activities.
This invention relates to a system for analyzing user activities to identify relevant tasks. The system processes user activity data to extract entities, such as objects, actions, or contexts, and compares them with task-related entities to determine matches. When a match is found, the system identifies a relevant task for the user. The system may also prioritize tasks based on the relevance of the matches or the frequency of user activities. The system can be used in productivity applications, task management tools, or digital assistants to improve task identification and automation. The invention addresses the problem of manually tracking and managing tasks by automating the process of identifying relevant tasks based on user behavior. The system enhances efficiency by reducing the need for manual task entry and improving task relevance through contextual analysis. The invention may also include features such as task prioritization, activity logging, and entity extraction to support the matching process. The system can operate in real-time or batch mode, depending on the application requirements. The invention is particularly useful in environments where users perform repetitive tasks or where task management is critical to productivity.
3. The system of claim 2, wherein the instructions that, when executed by the at least one processing device, further cause the system to infer the state of the user task based on a score from a machine learning process for determining the match between the task-related entity and a user activity.
A system for monitoring and analyzing user tasks in a computing environment addresses the challenge of accurately determining the state of a user's task based on observed activities. The system includes at least one processing device configured to execute instructions that enable the tracking of user activities and the identification of task-related entities. These entities are linked to specific tasks or objectives the user is working toward. The system further employs a machine learning process to evaluate the relationship between the task-related entities and the user's activities, generating a score that quantifies the match or alignment between them. This score is then used to infer the current state of the user's task, such as whether the task is progressing, stalled, or completed. The machine learning process may involve training models on historical data to improve the accuracy of state predictions. By dynamically assessing the relevance of user activities to the task at hand, the system provides insights into task progression and potential areas for intervention or optimization. This approach enhances productivity and task management in environments where user activities are monitored and analyzed for efficiency improvements.
7. The system of claim 1, wherein the triggering event comprises receiving an emailed receipt related to an user activity, wherein the instructions that, when executed by the at least one processing device, further cause the system to infer that the user task has been completed based on a connection in the user context graph between the user activity and at least one of the one or more task-related entities.
This invention relates to a system for automatically detecting task completion in a user activity monitoring system. The system addresses the problem of manually tracking and verifying whether a user has completed a task, which is inefficient and prone to human error. The system uses a user context graph to model relationships between user activities, tasks, and related entities, enabling automated task completion inference. The system includes a processing device that executes instructions to monitor user activities and detect triggering events. One such triggering event is receiving an emailed receipt related to a user activity. Upon detecting this event, the system analyzes the user context graph to determine if there is a connection between the user activity (e.g., making a purchase) and at least one task-related entity (e.g., a pending task to buy a product). If a connection exists, the system infers that the user task has been completed. The user context graph is a structured representation of relationships between user activities, tasks, and other relevant entities, allowing the system to automatically verify task completion without manual intervention. This approach improves efficiency and accuracy in task management by leveraging contextual data and automated reasoning.
8. The system of claim 1, wherein the instructions that, when executed by the at least one processing device, further cause the system to cease tracking the user task based on the state of the user task, or cause the system to persist the state of the user task as an uncompleted state, wherein the machine learning inference of the inferred status is based on signals collected from one or more sources of user data comprising at least one of location data, communication data, browsing history, web search history, application usage, or device usage.
A system monitors and manages user tasks by tracking their progress and determining task completion status using machine learning. The system collects data from multiple sources, including location data, communication logs, browsing history, web search history, application usage, and device usage. This data is analyzed to infer whether a user task has been completed or abandoned. If the system determines that a task is incomplete or abandoned, it can either stop tracking the task or save its current state as uncompleted. The machine learning model processes the collected signals to predict task status accurately, ensuring that incomplete tasks are properly managed without manual intervention. This approach improves task management efficiency by automating the detection of task abandonment and preserving task states for later resumption. The system dynamically adapts to user behavior patterns, enhancing productivity by reducing the need for manual task tracking.
9. The system of claim 1, wherein the inferred status of the implicit task or the inferred status of the explicit task supports status tracking operations corresponding to a completed, not completed, or in-progress state of the implicit task or explicit task.
This invention relates to a system for tracking the status of tasks, including both implicit and explicit tasks, to support workflow management. The system infers the status of tasks, which can be either implicit (not explicitly defined by a user) or explicit (directly specified by a user), and categorizes them into states such as completed, not completed, or in-progress. The inferred status is used to enable status tracking operations, allowing users or automated processes to monitor task progress. The system may include components for detecting task-related activities, analyzing contextual data, and determining task completion based on predefined criteria or learned patterns. By distinguishing between implicit and explicit tasks, the system provides a more comprehensive view of workflows, including those that may not be formally documented. The inferred status updates dynamically as new data is processed, ensuring real-time accuracy in tracking task progress. This approach improves productivity by reducing manual tracking efforts and providing actionable insights into task completion.
11. The system of claim 1, the event comprising the computer device state event, the computer device geo-location event, the computer application event, the computer file event, an operating system event, a date, a time, presence status, or a user interaction with a contact.
A system monitors and records various events related to computer devices and user activities to enhance security, compliance, and operational insights. The system tracks computer device state events, such as power status, connectivity, or hardware changes, and geo-location events to determine the physical location of the device. It also captures computer application events, including software launches, usage duration, and performance metrics, as well as computer file events, such as file access, modifications, or deletions. Operating system events, including system updates, logins, or error logs, are recorded to ensure system stability and security. The system logs dates, times, and presence status to monitor user availability and activity patterns. Additionally, it tracks user interactions with contacts, such as messages, calls, or shared files, to analyze communication behaviors. By aggregating these diverse event types, the system provides a comprehensive audit trail for security monitoring, forensic investigations, and compliance reporting. The recorded data can be used to detect anomalies, enforce policies, and improve system efficiency. The system may integrate with existing security frameworks or enterprise software to enhance its functionality.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
September 27, 2017
December 20, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.